Franchise Decision to Invest in Prominent Locations

Scrap Neighbourhoods Data - Geocoding Web Services - Foursquare Location Services

1. Import Libraries

2. Get 4 cities data from Wikipedia

City1: Bengaluru Data

https://en.wikipedia.org/wiki/List_of_wards_in_Bangalore

City2: Seoul Data

https://en.wikipedia.org/wiki/List_of_districts_of_Seoul

City3: Vancouver Data

https://en.wikipedia.org/wiki/List_of_neighbourhoods_in_Vancouver

City4: San Francisco Data

https://en.wikipedia.org/wiki/List_of_neighborhoods_in_San_Francisco

Merge 4 cities in one DataFrame

3. Getting Geocodes

Check Neighbourhoods Coordinates

Check Neighbourhoods with None Coordinates

Check Last Neighbourhoods with None Coordinates

4. Drawing Neighbourhoods/Cities Maps

Cities Map

Neighbourhoods Maps

5. Foursquare Location Services API

Getting Venues from Foursquare

API Test Request

API Venues Request

Save output DataFrames in one Excel File

Most common Venue Categories at each Neighbourhood

Bengaluru Venues

Seoul Venues

Vancouver Venues

San Francisco Venues

Save output DataFrames in one Excel File

6. Individual Clustering

Bengaluru Map

Bengaluru Clusters

Seoul Map

Seoul Clusters

Vancouver Map

Vancouver Clusters

San Francisco Map

San Francisco Clusters

Save output DataFrames in one Excel File

7. Complete Clustering